Revisiting Deep Learning Models for Tabular Data

TL;DR

This paper reviews deep learning models for tabular data, introduces two strong baseline architectures, and compares their performance with existing models and Gradient Boosted Decision Trees under standardized protocols.

Contribution

It identifies simple, effective deep architectures as strong baselines and provides a comprehensive comparison across multiple datasets with consistent protocols.

Findings

ResNet-like architecture is a strong baseline.

Transformer adaptation outperforms other models on most tasks.

No single model is universally best across all tabular datasets.

Abstract

The existing literature on deep learning for tabular data proposes a wide range of novel architectures and reports competitive results on various datasets. However, the proposed models are usually not properly compared to each other and existing works often use different benchmarks and experiment protocols. As a result, it is unclear for both researchers and practitioners what models perform best. Additionally, the field still lacks effective baselines, that is, the easy-to-use models that provide competitive performance across different problems. In this work, we perform an overview of the main families of DL architectures for tabular data and raise the bar of baselines in tabular DL by identifying two simple and powerful deep architectures. The first one is a ResNet-like architecture which turns out to be a strong baseline that is often missing in prior works. The second model is our simple adaptation of the Transformer architecture for tabular data, which outperforms other solutions on most tasks. Both models are compared to many existing architectures on a diverse set of tasks under the same training and tuning protocols. We also compare the best DL models with Gradient Boosted Decision Trees and conclude that there is still no universally superior solution.